WO2018210621A1 - Procédé d'établissement de règles numériques assisté par ordinateur permettant de surveiller le système technique - Google Patents

Procédé d'établissement de règles numériques assisté par ordinateur permettant de surveiller le système technique Download PDF

Info

Publication number
WO2018210621A1
WO2018210621A1 PCT/EP2018/061814 EP2018061814W WO2018210621A1 WO 2018210621 A1 WO2018210621 A1 WO 2018210621A1 EP 2018061814 W EP2018061814 W EP 2018061814W WO 2018210621 A1 WO2018210621 A1 WO 2018210621A1
Authority
WO
WIPO (PCT)
Prior art keywords
classes
technical system
rules
digital
abstract
Prior art date
Application number
PCT/EP2018/061814
Other languages
German (de)
English (en)
Inventor
Sebastian-Philipp Brandt
Gulnar MEHDI
Mikhail Roshchin
Thomas Runkler
Original Assignee
Siemens Aktiengesellschaft
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Siemens Aktiengesellschaft filed Critical Siemens Aktiengesellschaft
Priority to US16/612,981 priority Critical patent/US11521081B2/en
Priority to EP18727169.7A priority patent/EP3607473B1/fr
Priority to CN201880032809.9A priority patent/CN110637298B/zh
Publication of WO2018210621A1 publication Critical patent/WO2018210621A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/80—Information retrieval; Database structures therefor; File system structures therefor of semi-structured data, e.g. markup language structured data such as SGML, XML or HTML
    • G06F16/84—Mapping; Conversion
    • G06F16/86—Mapping to a database
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/02—Knowledge representation; Symbolic representation
    • G06N5/022—Knowledge engineering; Knowledge acquisition
    • G06N5/025—Extracting rules from data
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0208—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the configuration of the monitoring system
    • G05B23/0213—Modular or universal configuration of the monitoring system, e.g. monitoring system having modules that may be combined to build monitoring program; monitoring system that can be applied to legacy systems; adaptable monitoring system; using different communication protocols
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
    • G06F11/3013—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is an embedded system, i.e. a combination of hardware and software dedicated to perform a certain function in mobile devices, printers, automotive or aircraft systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3089—Monitoring arrangements determined by the means or processing involved in sensing the monitored data, e.g. interfaces, connectors, sensors, probes, agents
    • G06F11/3093—Configuration details thereof, e.g. installation, enabling, spatial arrangement of the probes

Definitions

  • the invention relates to a method and a device for the computer-aided creation of digital rules for monitoring a technical system. Furthermore, the invention relates to a method and a device for monitoring a technical system as well as a computer program product and a computer program.
  • Rule-based monitoring methods for technical systems are known from the prior art in order to diagnose the operation of the technical system and to recognize or predict malfunctions at an early stage.
  • digital rules are brought by a control machine for the execution, with the rules depending on certain criteria detect irregularities in the operation of the technical system and for example, output entspre ⁇ sponding alerts.
  • Rule-based procedures for monitoring technical systems are specifically adapted to the components of the system to be monitored, ie, device-specific device identifiers are used to designate the components in the digital rules.
  • re ⁇ yellow-based methods are always designed individually for the corresponding technical system and can not be readily transferred to another technical system, even if this has the same or a similar structure.
  • the object of the invention is therefore to provide a method for the computer-aided creation of digital rules for monitoring a technical system, with which rules created by a user can be used in a simple manner for a plurality of technical systems.
  • This object is achieved by the independent claims ge ⁇ triggers. Further developments of the invention are defined in the dependent claims.
  • an ontology including a plurality of classes including classes of components of the technical system and classes of operational state characteristics of the technical system, and semantic relations between the classes.
  • the components are appropriate Bestandtei ⁇ le of the technical system.
  • a component may also relate to the technical system as a whole.
  • Preferably ⁇ summarize the classes of component classes of components of the technical system without sensor function and classes of sensors. Classes of components without sensor function are functional units that relate to an operating function that is not directly related to sensed measured values. Nonetheless, such classes of components may also contain sensors.
  • the classes of operating state characteristics of the technical system depend on state variables of the technical system. Examples of such classes are mentioned below.
  • relations known in ontology can be used, such as a relation specifying that one class is a subclass of another class, or a relation specifying that one class is part of another class.
  • the defi ⁇ nition of other relations depending on the present in the ontology classes is within the framework of craftsmanship action. If the ontology contains, for example, the classes of operating processes described below, then describe a relation also that a class of a component is involved in a class of an operating process.
  • a user interface comprising a visual display, wherein a user can create abstract rule formulations based on the classes and the semantic relations of the ontology via the user interface using the visual display.
  • the user-created rule formulations are saved as digital abstract rules.
  • the digital abstract rules are stored in XML format.
  • the digital abstract rules automates for the technical system as digital concrete rules instantiated by the classes of components in the digital abstract rules are mapped to specific Adjustidentifikatio ⁇ nen of the technical system with access to a database containing data on the technical system and converting the classes of operating state characteristics into operating system characteristics specific to the technical system, including the specific device identifications.
  • an automated mapping of a generic rule language to a rule language specific to the system to be monitored takes place. This results in the pre ⁇ part that abstract rules for identical or similar technical ⁇ cal systems by the user do not have to be created each time for the special technical system but used by appropriate instantiation several times for identical or similar Liehe technical systems can be.
  • the mapping of the classes of components in the digital abstract rules to the specific device identifications of the technical system is based on the R2RML (RDB to RDF Mapping Language) language. It is a language standard of the W3C consortium to map information from relationa ⁇ len databases into RDF records an ontology.
  • the classes of components contain not only individual components but also classes of functional groups comprising a plurality of subcomponents.
  • a class of a functional group may refer to an oil system or a gas path in the technical system.
  • At least one class for describing an average value of a state variable in the technical system at least one class for describing a temporal change of a state variable in the technical system.
  • classes of ontology further contain classes of abstract rules which the user can take into account when creating the abstract rule formulations and which are instantiated as corresponding concrete rules. In this way, the user is already given control blocks for creating the abstract rule, so that the rule creation is simplified.
  • the classes of cytology further include classes of operational processes that a user may consider when creating an abstract rule formulation, wherein in the instantiation of the digital concrete rules, classes of operational processes in the digital abstract rules access the above database specific operating process identifications of the technical system are mapped. This operating process ⁇ identifications are then contained in the specific for the technical system operating condition characteristics.
  • Sol ⁇ che operation processes can relate for example to a startup process or a power-off of the technical Sys tems ⁇ .
  • a query interface will be ⁇ riding made in the inventive method further with which a user can query based on the classes and the semantic relations of ontology operating data of the technical system. This is possible if the above database contains such operating data. Gege ⁇ appropriate, this variant can also be used online during operation of the technical system to access operational data on current loading.
  • the inventive method can be used to create rules for any technical systems.
  • Insbeson ⁇ particular, the to be monitored technical system, an electrical see power generation plant or an electric power ⁇ network or a turbine, such as a gas turbine, or an automation system or a means of transport such as a train, or a medical device, such as a Computertomo ⁇ graph or a magnetic resonance tomograph, be.
  • Under an automation system is an industrial plant for the automated implementation of processes and in particular for the automated production or production of products to understand.
  • the invention further relates to a method for monitoring a technical system, wherein digital concrete rules with the method according to the invention just described or one or more preferred variants of this method are generated and then executed with a rule machine on the technical system for its monitoring ,
  • the invention further relates to a device for the computer-aided creation of digital rules for monitoring a technical system, wherein the device is configured such that it performs the inventive method for creating digital rules or one or more preferred variants of this method.
  • the invention relates to a device for monitoring a technical system, which is set up for carrying out the above-described method for monitoring a technical system.
  • the invention further relates to a computer program product having a program code stored on a machine-readable carrier for carrying out the method according to the invention for creating digital rules or for
  • the invention comprises a computer program with a program code for carrying out the method according to the invention for creating digital rules or for carrying out the method according to the invention for monitoring a technical system when the program code is executed on a computer.
  • FIG. 1 shows a schematic representation of the essential steps of a variant of the method according to the invention.
  • the method described with reference to FIG. 1 serves for the computer-assisted creation of rules for a specific technical system in order to monitor the operation of the technical system with these rules.
  • the aim is to provide a user with an interface for formulating abstract rules, which are then transformed into concrete rules for the specific technical system.
  • a user interface UI shown only schematically in the method used for rule creation, which summarizes a visual indication on a display implement and with the via appropriate user actions, in ⁇ play performed through a cursor and a computer ⁇ mouse, abstract rules can be created.
  • These abstract ⁇ th rules are generally designated in Fig. 1 with AR.
  • classes knockout of components of the technical system
  • classes of BZ operating state characteristics of the technical system and ⁇ rule classes BP of operating processes in the technical system are provided.
  • the ontology contains classes RK of abstract rules that can be used as building blocks in the creation of the abstract rules AR. NEN.
  • the classes mentioned are indicated in Fig. 1 only schematically by corresponding rectangles.
  • the relations include, inter alia, a relation specifying that one class is a subclass of another class, and a relation specifying that one class is a part of another class.
  • the relations also contain relations which describe that a component of the technical system is involved in a specific operating process or rule.
  • other semantic relations are also provided, whereby the corresponding definition of such relations lies within the scope of expert action.
  • Examples of classes KO of components in the above cytology ON are parts of a gas turbine, e.g. certain rotor blades or certain sensors which acquire measurement data, such as Sensors for measuring combustion chamber temperatures or sensors for measuring rotor speeds.
  • classes BZ of operating state characteristics are state variables measured in the gas turbine, such as state variables.
  • a class BZ of an operating condition characteristic is a so-called time trend, which specifies a longer-term temporal evolution of a state quantity.
  • Fer ⁇ ner can specify the mode characteristics increases or decreases of state variables, with the increase and the decrease possibly also classified to whether there is a strong, medium or weak increase or decrease.
  • classes BP of operating processes are the start-up or shutdown of the considered gas turbine.
  • a class RK of an abstract rule can pretend, in the manner of a template, that there is a certain error in the gas turbine when measured variables run out of a certain value range.
  • a user can now create various abstract rules AR via the user interface UI, accessing the named classes and semantic relations of the ontology ON, which are stored in XML format in the exemplary embodiment considered here.
  • An example of such an abstract rule may be such that, in the event that the average speed of a rotor measured via a speed sensor exceeds a predetermined limit over a predetermined period of time and, at the same time, a sharp rise in a combustor temperature in the gas turbine over that time period is present, a Warn ⁇ message during the operation of the technical system is madege ⁇ ben.
  • the user-created abstract rules AR are gener- ally formulated for components of the technical system and must now be set in relation to specific components of the system under consideration, ie in the present case a special gas turbine.
  • the abstract rules AR are instantiated in an instantiation step IN, ie they are converted into concrete rules KR.
  • the classes KO of components and classes BP contained in the abstract rules are converted from operational processes into concrete identifications.
  • the classes KO device identifications GID and the classes BP process identifiers PID are assigned, said identifica ⁇ functions are unique to the concrete to be monitored gas turbine. It thus becomes a mapping MP of generic classes carried out on concrete identifications.
  • the classes BZ of operating state characteristics are converted into concrete operating state characteristics as part of a translation step TR, these characteristics now containing corresponding device identifications GID and process identifications PID, respectively.
  • mapping MP accessed information from a database DB, which specifies con- crete data to be monitored technical system and in particular the device identifications and pro ⁇ zessidenttechniken contains.
  • the mapping is performed in the variant considered here based on the known per se language standard R2RML.
  • the architecture of FIG. 1 also provides a query interface IF using, for example, the per-query SPARQL as it is known per se.
  • a query ⁇ interface a user can extract information about the technical system from the database DB using the terminology of the ontology ON.
  • An example of such a query is the search for all Automaticidenti- fications of sensors contained in a particular component of the technical system and in the involved from ⁇ s Thermalen rule "analysis of vibrations in the technical system.”
  • the architecture of Fig. 1 may also be coupled directly to the technical system to be monitored, so that during monitoring the technical system via the query interface IF ak ⁇ tual measured values can be read out.
  • the embodiment of the invention described above has a number of advantages.
  • the possibility is created to easily formulate abstract rules for the monitoring of a technical system, these rules being automatically translated into concrete rules for the technical system under consideration.
  • the effort to create rules is thereby significantly reduced. This could be proven by experiments.
  • users have created corresponding rules directly in the specific rule language of the technical system as well as using the ontology according to the invention.
  • the creation of the abstract rules based on the ontology could be done much faster by the user than based on the concrete rule ⁇ language.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Quality & Reliability (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • Automation & Control Theory (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Testing And Monitoring For Control Systems (AREA)
  • Stored Programmes (AREA)

Abstract

L'invention concerne un procédé d'établissement de règles numériques assisté par ordinateur permettant de surveiller un système technique. Selon le procédé, une cytologie (ON) est utilisée, laquelle comporte une pluralité de classes comportant des classes (KO) de composants du système technique et des classes (BZ) de caractéristiques d'état de fonctionnement du système technique, ainsi que des relations sémantiques (SR) entre les classes. Au moyen d'une interface utilisateur (UI), un utilisateur peut formuler des règles abstraites (AR) en utilisant les classes et les relations sémantiques (SR) à partir de l'ontologie (ON). Ces règles abstraites (AR) sont automatiquement converties en règles concrètes (KR) valables pour le système technique spécifique. Le procédé présente l'avantage que des règles correspondantes ne doivent plus être formulées individuellement par l'utilisateur pour des systèmes techniques individuels, mais des règles abstraites ne doivent être créées qu'une seule fois pour des systèmes techniques identiques ou similaires. Ces règles peuvent ainsi être automatiquement instanciées pour les machines respectives du système technique spécifique. Le procédé selon l'invention peut être utilisé pour tout système technique, tel que des installation de production d'énergie électriques, des réseaux d'énergie électriques, des turbines, des installations d'automatisation, des moyens de transport, des appareils médicaux et analogues.
PCT/EP2018/061814 2017-05-18 2018-05-08 Procédé d'établissement de règles numériques assisté par ordinateur permettant de surveiller le système technique WO2018210621A1 (fr)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US16/612,981 US11521081B2 (en) 2017-05-18 2018-05-08 Method for the computer aided creation of digital rules for monitoring the technical system
EP18727169.7A EP3607473B1 (fr) 2017-05-18 2018-05-08 Procédé d'établissement de règles numériques assisté par ordinateur permettant de surveiller le système technique
CN201880032809.9A CN110637298B (zh) 2017-05-18 2018-05-08 计算机辅助地制订用于监控技术系统的数字规则的方法

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
EP17171786.1A EP3404558A1 (fr) 2017-05-18 2017-05-18 Procédé d'élaboration assisté par ordinateur de règles numériques destinées à surveiller le système technique
EP17171786.1 2017-05-18

Publications (1)

Publication Number Publication Date
WO2018210621A1 true WO2018210621A1 (fr) 2018-11-22

Family

ID=59030757

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2018/061814 WO2018210621A1 (fr) 2017-05-18 2018-05-08 Procédé d'établissement de règles numériques assisté par ordinateur permettant de surveiller le système technique

Country Status (4)

Country Link
US (1) US11521081B2 (fr)
EP (2) EP3404558A1 (fr)
CN (1) CN110637298B (fr)
WO (1) WO2018210621A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3404558A1 (fr) * 2017-05-18 2018-11-21 Siemens Aktiengesellschaft Procédé d'élaboration assisté par ordinateur de règles numériques destinées à surveiller le système technique

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005010625A2 (fr) * 2003-07-22 2005-02-03 Siemens Aktiengesellschaft Procede pour generer une representation de structure decrivant une installation d'automatisation specifique
WO2015074871A1 (fr) * 2013-11-21 2015-05-28 Siemens Aktiengesellschaft Système de création informatisée de règles de surveillance et/ou de diagnostic d'une installation technique

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE10356399B4 (de) * 2003-12-03 2006-06-14 Ontoprise Gmbh Datenverarbeitungssystem
US8522195B2 (en) * 2007-09-14 2013-08-27 Exigen Properties, Inc. Systems and methods to generate a software framework based on semantic modeling and business rules
CN103727639B (zh) * 2014-01-09 2016-09-07 山东建筑大学 基于本体的中央空调节能系统及方法
EP3404558A1 (fr) * 2017-05-18 2018-11-21 Siemens Aktiengesellschaft Procédé d'élaboration assisté par ordinateur de règles numériques destinées à surveiller le système technique

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005010625A2 (fr) * 2003-07-22 2005-02-03 Siemens Aktiengesellschaft Procede pour generer une representation de structure decrivant une installation d'automatisation specifique
WO2015074871A1 (fr) * 2013-11-21 2015-05-28 Siemens Aktiengesellschaft Système de création informatisée de règles de surveillance et/ou de diagnostic d'une installation technique

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
GULNAR MEHDI ET AL: "Towards Semantic Reasoning in Knowledge Management Systems", PROCEEDINGS OF THE 4TH INTERNATIONAL WORKSHOP ON ARTIFICIAL INTELLIGENCE FOR KNOWLEDGE MANAGEMENT, 9 July 2016 (2016-07-09), New York City, pages 1 - 7, XP055393046 *
LISA THERESA ABELE: "Resource Monitoring in Industrial Manufacturing Using Knowledge-Based Technologies", 28 April 2014 (2014-04-28), pages 1 - 227, XP055393038, Retrieved from the Internet <URL:www.researchgate.net> [retrieved on 20170721] *

Also Published As

Publication number Publication date
US11521081B2 (en) 2022-12-06
EP3404558A1 (fr) 2018-11-21
EP3607473B1 (fr) 2022-03-30
CN110637298A (zh) 2019-12-31
EP3607473A1 (fr) 2020-02-12
US20200160193A1 (en) 2020-05-21
CN110637298B (zh) 2023-10-10

Similar Documents

Publication Publication Date Title
DE102017102651A1 (de) Vorrichtung zum Formulieren von Regeln in einem Prozesssteuerungsnetzwerk
DE112019002030T5 (de) Qualitätsüberprüfungs-Verwaltungssystem mit konfigurierbaren Ausnahmeregeln
DE102011053544A1 (de) Verfahren und Vorrichtung zur Anzeige von Prozessregelungsinformationen
WO2017182312A1 (fr) Système de gestion de cycle de vie pour composants d&#39;installations
WO2005119381A1 (fr) Systeme d&#39;utilisation d&#39;une installation par edition d&#39;objets graphiques
DE10346478A1 (de) Flexibler Softwareupdate für Automatisierungssysteme über Internet
DE112017005957T5 (de) Informationsverarbeitungssystem und Informationsverarbeitungsverfahren
EP2927819A1 (fr) Procédé de traitement automatique de plusieurs fichiers journaux d&#39;un système d&#39;automatisation
EP0768584A1 (fr) Méthode de surveillance d&#39;une machine ou installation
EP2804061A1 (fr) Procédé de surveillance d&#39;une installation de processus et/ou de fabrication
EP2414903A1 (fr) Dispositif et procédé de réalisation d&#39;un modèle de processus
DE112019005467T5 (de) System und verfahren zum erkennen und vorhersagen von mustern eines anomalen sensorverhaltens einer maschine
WO2020078940A1 (fr) Dispositif, procédé et programme informatique pour le traitement automatiquement d&#39;identifiants de données
EP3047341B1 (fr) Système de création informatisée de règles de surveillance et/ou de diagnostic d&#39;une installation technique
WO2018210621A1 (fr) Procédé d&#39;établissement de règles numériques assisté par ordinateur permettant de surveiller le système technique
DE60127543T2 (de) System mit web-/wap-schnittstelle zur überwachung der erzeugung elektrischer energie
EP3968149A1 (fr) Génération des règles de commande à partir d&#39;un régulateur schématisé
EP1646917B1 (fr) Procede pour generer une representation de structure decrivant une installation d&#39;automatisation specifique
AT523586A1 (de) Verfahren zur zumindest teilweise dezentralen Berechnung des Gesundheitszustandes von mindestens einer Windkraftanlage
DE68905848T2 (de) Speicherprogrammierbare steuerung mit strukturierter programmiersprache.
EP1014054A2 (fr) Procédé de contrôle des machines rotatives se basant sur un model diagnostique des vibrations
CN114245895A (zh) 为至少两个日志文件生成一致表示的方法
EP3824359B1 (fr) Conception, configuration et maintien d&#39;un dispositif d&#39;entraînement
EP4120069A1 (fr) Transformation d&#39;une application en une description sémantique
WO2012013203A1 (fr) Système et procédé de diffusion et d&#39;échange d&#39;éléments pour la planification et/ou pour l&#39;exploitation de moyens opérationnels en technique d&#39;automatisme

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18727169

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2018727169

Country of ref document: EP

Effective date: 20191105